deepset-ai / deepset-ai/haystack
OpenAI's Batch API Support
@julian-risch is already working on this.
Since Aug 7, 2026.
- Dominant language
- Python
- Stars
- 26.6k
- Forks
- 3.2k
- Avg merge
- 1d 3h
- Merged PRs (30d)
- 194
Description
Is your feature request related to a problem? Please describe.
Currently, Haystack doesn’t support OpenAI’s batch API, which limits throughput and efficiency when processing large amounts of data with OpenAI models. This leads to higher latency and increased costs due to individual API calls for each request.
Describe the solution you'd like
I’d like to see Haystack support or enable leveraging the capabilities of OpenAI’s batch API.
Describe alternatives you've considered
I’ve considered workarounds, such as building a custom component that sends requests to a server, collects several requests for batching, and returns the results after processing. However, this approach would require running hundreds of pipeline instances in parallel, adding significant complexity.
Additional context
Batch API support would be a valuable enhancement, particularly for large-scale applications. Any information on potential plans or timelines for this feature would be appreciated.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.